BlingFireNuget 0.1.5

There is a newer version of this package available.
See the version list below for details. 
dotnet add package BlingFireNuget --version 0.1.5                

                    
                

            
NuGet\Install-Package BlingFireNuget -Version 0.1.5
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="BlingFireNuget" Version="0.1.5" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add BlingFireNuget --version 0.1.5                

                    
                

            
#r "nuget: BlingFireNuget, 0.1.5"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
// Install BlingFireNuget as a Cake Addin
#addin nuget:?package=BlingFireNuget&version=0.1.5

// Install BlingFireNuget as a Cake Tool
#tool nuget:?package=BlingFireNuget&version=0.1.5

Bling Fire

Introduction

Hi, we are a team at Microsoft called Bling (Beyond Language Understanding), we help Bing be smarter. Here we wanted to share with all of you our FInite State machine and REgular expression manipulation library (FIRE). We use Fire for many linguistic operations inside Bing such as Tokenization, Multi-word expression matching, Unknown word-guessing, Stemming / Lemmatization just to mention a few.

Bling Fire Tokenizer Overview

Bling Fire Tokenizer provides state of the art performance for Natural Language text tokenization. Bling Fire supports four tokenization algorithms:

  1. Pattern-based tokenization
  2. WordPiece tokenization
  3. SentencePiece Unigram LM
  4. SentencePiece BPE

Bling Fire provides uniform interface for working with all four algorithms so there is no difference for the client whether to use tokenizer for XLNET, BERT or your own custom model.

Model files describe the algorithms they are built for and are loaded on demand from external file. There are also two default models for NLTK-style tokenization and sentence breaking, which does not need to be loaded. The default tokenization model follows logic of NLTK, except hyphenated words are split and a few "errors" are fixed.

Normalization can be added to each model, but is optional.

Diffrences between algorithms are summarized here.

Bling Fire Tokenizer high level API designed in a way that it requires minimal or no configuration, or initialization, or additional files and is friendly for use from languages like Python, Ruby, Rust, C#, JavaScript (via WASM), etc.

We have precompiled some popular models and listed with the source code reference below:

File Name Models it should be used for Algorithm Source Code
wbd.bin Default Tokenization Model Pattern-based src
sbd.bin Default model for Sentence breaking Pattern-based src
bert_base_tok.bin BERT Base/Large WordPiece src
bert_base_cased_tok.bin BERT Base/Large Cased WordPiece src
bert_chinese.bin BERT Chinese WordPiece src
bert_multi_cased.bin BERT Multi Lingual Cased WordPiece src
xlnet.bin XLNET Tokenization Model Unigram LM src
xlnet_nonorm.bin XLNET Tokenization Model /wo normalization Unigram LM src
bpe_example.bin A model to test BPE tokenization BPE src
xlm_roberta_base.bin XLM Roberta Tokenization Unigram LM src
laser100k.bin Trained on balanced by language WikiMatrix corpus of 80+ languages Unigram LM src
uri250k.bin URL tokenization model trained on random URLs from the web Unigram LM src

Oh yes, it is also the fastest! We did a comparison of Bling Fire with tokenizers from Hugging Face, Bling Fire runs 4-5 times faster than Hugging Face Tokenizers, see also Bing Blog Post. We did comparison of Bling Fire Unigram LM and BPE implementaion to the same one in SentencePiece library and our implementation is ~2x faster, see XLNET benchmark and BPE benchmark. Not to mention our default models are 10x faster than the same functionality from SpaCy, see benchmark wiki and this Bing Blog Post.

So if low latency inference is what you need then you have to try Bling Fire!

There are no supported framework assets in this package.

Learn more about Target Frameworks and .NET Standard.

  • .NETCoreApp 3.1

    • No dependencies.

NuGet packages (2)

Showing the top 2 NuGet packages that depend on BlingFireNuget:

Package Downloads
SS.SemanticKernel.Extensions

This is a SemanticKernel extension built on the Embedding codebase.
BlingFireNetStandard

BlingFire wrapper for .Net Standard, see https://github.com/microsoft/BlingFire for details.

GitHub repositories (1)

Showing the top 1 popular GitHub repositories that depend on BlingFireNuget:

Repository Stars
Azure-Samples/semantic-kernel-rag-chat
Tutorial for ChatGPT + Enterprise Data with Semantic Kernel, OpenAI, and Azure Cognitive Search
Version Downloads Last updated
0.1.8 32,723 9/24/2021
0.1.7 1,502 5/25/2021
0.1.6 1,754 4/7/2021
0.1.5 913 3/11/2021
0.1.4 2,420 7/7/2020

BlingFire wrapper for .Net Core, see https://github.com/microsoft/BlingFire for details.